© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2231
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts, particularly involving polynomials and vector spaces

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jereo
    -0.61
     ویکی‌پدی
    -0.59
     pinulongan
    -0.58
     ourselves
    -0.55
     Paglinawan
    -0.54
     Ephraim
    -0.50
    ]--;
    -0.50
    himself
    -0.48
     vru
    -0.47
    RTSC
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.60
    gemeester
    0.57
    مصادر
    0.54
     الحره
    0.54
    ∭
    0.54
     dataSnapshot
    0.52
    Unsubscribe
    0.52
    preduce
    0.51
    werp
    0.50
    ugier
    0.50
    Activations Density 0.112%

    No Known Activations